Flexible conditional image generation of missing data with learned mental maps
File(s)
Accepted version
OA Location
Author(s)
Hou, Benjamin
Vlontzos, Athanasios
Alansary, Amir
Rueckert, Daniel
Kainz, Bernhard
Type
Conference Paper
Abstract
Real-world settings often do not allow acquisition of high-resolution volumetric images for accurate morphological assessment and diagnostic. In clinical practice it is frequently common to acquire only sparse data (e.g. individual slices) for initial diagnostic decision making. Thereby, physicians rely on their prior knowledge (or mental maps) of the human anatomy to extrapolate the underlying 3D information. Accurate mental maps require years of anatomy training, which in the first instance relies on normative learning, i.e. excluding pathology. In this paper, we leverage Bayesian Deep Learning and environment mapping to generate full volumetric anatomy representations from none to a small, sparse set of slices. We evaluate proof of concept implementations based on Generative Query Networks (GQN) and Conditional BRUNO using abdominal CT and brain MRI as well as in a clinical application involving sparse, motion-corrupted MR acquisition for fetal imaging. Our approach allows to reconstruct 3D volumes from 1 to 4 tomographic slices, with a SSIM of 0.7+ and cross-correlation of 0.8+ compared to the 3D ground truth.
Date Issued
2020-10-24
Date Acceptance
2019-08-20
Citation
MLMIR 2019: Machine Learning for Medical Image Reconstruction, 2020, 11905 LNCS, pp.139-150
ISBN
9783030338428
ISSN
0302-9743
Publisher
Springer International Publishing
Start Page
139
End Page
150
Journal / Book Title
MLMIR 2019: Machine Learning for Medical Image Reconstruction
Volume
11905 LNCS
Copyright Statement
© Springer Nature Switzerland AG 2019. The final publication is available at Springer via https://link.springer.com/chapter/10.1007%2F978-3-030-33843-5_13
Source
Machine Learning for Medical Image Reconstruction: Second International Workshop
Subjects
Artificial Intelligence & Image Processing
Publication Status
Published
Start Date
2019-10-17
Coverage Spatial
Shenzhen, China
Date Publish Online
2019-10-24